计算机工程 ›› 2019, Vol. 45 ›› Issue (10): 301-307.doi: 10.19678/j.issn.1000-3428.0052812

• 开发研究与工程应用 • 上一篇    下一篇

基于卷积神经网络的无线电广播同频干扰检测

刘雨灵1, 侯进1, 张笑语2, 陈曾2   

  1. 1. 西南交通大学 信息科学与技术学院, 成都 611756;
    2. 成都华日通讯技术有限公司, 成都 610045
  • 收稿日期:2018-10-08 修回日期:2018-11-20 出版日期:2019-10-15 发布日期:2018-11-29
  • 作者简介:刘雨灵(1995-),女,硕士研究生,主研方向为计算机视觉、深度学习;侯进(通信作者),副教授、博士;张笑语,高级工程师、硕士;陈曾,硕士。
  • 基金项目:
    浙江大学CAD&CG国家重点实验室开放课题(A1923);成都市科技惠民技术研发项目(2015-HM01-00050-SF)。

Same Frequency Interference Detection in Radio Broadcast Based on Convolutional Neural Network

LIU Yuling1, HOU Jin1, ZHANG Xiaoyu2, CHEN Zeng2   

  1. 1. School of Information Science and Technology, Southwest Jiaotong University, Chengdu 611756, China;
    2. Chengdu Huari Communication Technology Co., Ltd., Chengdu 610045, China
  • Received:2018-10-08 Revised:2018-11-20 Online:2019-10-15 Published:2018-11-29

摘要: 针对无线电干扰中较为突出的同频干扰问题,将深度学习应用于干扰信号检测,提出一种无线电调频广播同频干扰检测算法。将调频广播数据转化为能体现信号特性的小波变换时频图,并将其作为卷积神经网络(CNN)的训练数据,训练CNN学习信号的时频特征,得到干扰检测模型。实验结果表明,与传统的机器学习算法相比,该算法能更准确地检测出广播信号中是否存在同频干扰信号,其干扰检测准确率达95.0%。

关键词: 同频干扰, 调频广播信号, 卷积神经网络, 小波变换, 特征提取

Abstract: Aiming at the problem of same frequency interference which is rather prominent in radio interference,deep learning is applied to the interference signals detection,and a new algorithm for detecting same frequency interference in frequency modulation broadcast is proposed.Transform the frequency modulation broadcast signals into the time-frequency images of wavelet which can reflect the signal characteristics, and then those images are used as the training data of the Convolutional Neural Network(CNN).After training the CNN to learn the time-frequency features of the signal,the detection model is obtained.Experimental results show that,compared with the traditional machine learning algorithm,the proposed algorithm can detect whether there is same frequency interference signal in the broadcast signal more accurately,and the accuracy can reach 95.0%.

Key words: same frequency interference, frequency modulation broadcast signal, Convolutional Neural Network(CNN), wavelet transform, feature extraction

中图分类号: